We present a cluster-based volume rendering system for roaming very large volumes. This system allows to move a gigabyte-sized probe inside a total volume of several tens or hundreds of gigabytes in real-time. While t...
详细信息
We present a cluster-based volume rendering system for roaming very large volumes. This system allows to move a gigabyte-sized probe inside a total volume of several tens or hundreds of gigabytes in real-time. While the size of the probe is limited by the total amount of texture memory on the cluster, the size of the total data set has no theoretical limit. The cluster is used as a distributed graphics processing unit that both aggregates graphics power and graphics memory. A hardware-accelerated volume renderer runs in parallel on the cluster nodes and the final image compositing is implemented using a pipelined sort-last rendering algorithm. Meanwhile, volume bricking and volume paging allow efficient data caching. On each rendering node, a distributed hierarchical cache system implements a global software-based distributed shared memory on the cluster. In case of a cache miss, this system first checks page residency on the other cluster nodes instead of directly accessing local disks. Using two Gigabit Ethernet network interfaces per node, we accelerate data fetching by a factor of 4 compared to directly accessing local disks. The system also implements asynchronous disk access and texture loading, which makes it possible to overlap data loading, volume slicing and rendering for optimal volume roaming.
Volumetric datasets with multiple variables on each voxel over multiple time steps are often complex, especially when considering the exponentially large attribute space formed by the variables in combination with the...
详细信息
Volumetric datasets with multiple variables on each voxel over multiple time steps are often complex, especially when considering the exponentially large attribute space formed by the variables in combination with the spatial and temporal dimensions. It is intuitive, practical, and thus often desirable, to interactively select a subset of the data from within that high-dimensional value space for efficient visualization. This approach is straightforward to implement if the dataset is small enough to be stored entirely in-core. However, to handle datasets sized at hundreds of gigabytes and beyond, this simplistic approach becomes infeasible and thus, more sophisticated solutions are needed. In this work, we developed a system that supports efficient visualization of an arbitrary subset, selected by range-queries, of a large multivariate time-varying dataset. By employing specialized data structures and schemes of data distribution, our system can leverage a large number of networked computers as paralleldata servers, and guarantees a near optimal load-balance. We demonstrate our system of scalable data servers using two large time-varying simulation datasets.
Focus+context visualization integrates a visually accentuated representation of selected data items in focus (more details, more opacity, etc.) with a visually deemphasized representation of the rest of the data, i.e....
详细信息
Focus+context visualization integrates a visually accentuated representation of selected data items in focus (more details, more opacity, etc.) with a visually deemphasized representation of the rest of the data, i.e., the context. The role of context visualization is to provide an overview of the data for improved user orientation and improved navigation. A good overview comprises the representation of both outliers and trends. Up to now, however, context visualization not really treated outliers sufficiently. In this paper we present a new approach to focus+context visualization in parallel coordinates which is truthful to outliers in the sense that small-scale features are detected before visualization and then treated specially during context visualization. Generally, we present a solution which enables context visualization at several levels of abstraction, both for the representation of outliers and trends. We introduce outlier detection and context generation to parallel coordinates on the basis of a binned data representation. This leads to an output-oriented visualization approach which means that only those parts of the visualization process are executed which actually affect the final rendering. Accordingly, the performance of this solution is much more dependent on the visualization size than on the data size which makes it especially interesting for largedatasets. Previous approaches are outperformed, the new solution was successfully applied to datasets with up to 3 million data records and up to 50 dimensions.
Categorical data dimensions appear in many real-world data sets, but few visualization methods exist that properly deal with them. parallel Sets are a new method for the visualization and interactive exploration of ca...
详细信息
Categorical data dimensions appear in many real-world data sets, but few visualization methods exist that properly deal with them. parallel Sets are a new method for the visualization and interactive exploration of categorical data that shows data frequencies instead of the individual data points. The method is based on the axis layout of parallel coordinates, with boxes representing the categories and parallelograms between the axes showing the relations between categories. In addition to the visual representation, we designed a rich set of interactions. parallel Sets allow the user to interactively remap the data to new categorizations and, thus, to consider more data dimensions during exploration and analysis than usually possible. At the same time, a metalevel, semantic representation of the data is built. Common procedures, like building the cross product of two or more dimensions, can be performed automatically, thus complementing the interactive visualization. We demonstrate parallel Sets by analyzing a large CRM data set, as well as investigating housing data from two US states.
We present a cluster-based volume rendering system for roaming very large volumes. This system allows to move a gigabyte-sized probe inside a total volume of several tens or hundreds of gigabytes in real-time. While t...
详细信息
We present a cluster-based volume rendering system for roaming very large volumes. This system allows to move a gigabyte-sized probe inside a total volume of several tens or hundreds of gigabytes in real-time. While the size of the probe is limited by the total amount of texture memory on the cluster, the size of the total data set has no theoretical limit. The cluster is used as a distributed graphics processing unit that both aggregates graphics power and graphics memory. A hardware-accelerated volume renderer runs in parallel on the cluster nodes and the final image compositing is implemented using a pipelined sort-last rendering algorithm. Meanwhile, volume bricking and volume paging allow efficient data caching. On each rendering node, a distributed hierarchical cache system implements a global software-based distributed shared memory on the cluster. In case of a cache miss, this system first checks page residency on the other cluster nodes instead of directly accessing local disks. Using two Gigabit Ethernet network interfaces per node, we accelerate data fetching by a factor of 4 compared to directly accessing local disks. The system also implements asynchronous disk access and texture loading, which makes it possible to overlap data loading, volume slicing and rendering for optimal volume roaming.
Business data is often presented using simple business graphics. These familiar visualizations are effective for providing overviews, but fall short for the presentation of large amounts of detailed information. Treem...
详细信息
Business data is often presented using simple business graphics. These familiar visualizations are effective for providing overviews, but fall short for the presentation of large amounts of detailed information. Treemaps can provide such detail, but are often not easy to understand. We present how standard treemap algorithms can be adapted such that the results mimic familiar business graphics. Specifically, we present the use of different layout algorithms per level, a number of variations of the squarified algorithm, the use of variable borders, and the use of non-rectangular shapes. The combined use of these leads to histograms, pie charts and a variety of other styles.
Volumetric datasets with multiple variables on each voxel over multiple time steps are often complex, especially when considering the exponentially large attribute space formed by the variables in combination with the...
详细信息
Volumetric datasets with multiple variables on each voxel over multiple time steps are often complex, especially when considering the exponentially large attribute space formed by the variables in combination with the spatial and temporal dimensions. It is intuitive, practical, and thus often desirable, to interactively select a subset of the data from within that high-dimensional value space for efficient visualization. This approach is straightforward to implement if the dataset is small enough to be stored entirely in-core. However, to handle datasets sized at hundreds of gigabytes and beyond, this simplistic approach becomes infeasible and thus, more sophisticated solutions are needed. In this work, we developed a system that supports efficient visualization of an arbitrary subset, selected by range-queries, of a large multivariate time-varying dataset. By employing specialized data structures and schemes of data distribution, our system can leverage a large number of networked computers as paralleldata servers, and guarantees a near optimal load-balance. We demonstrate our system of scalable data servers using two large time-varying simulation datasets.
Categorical data dimensions appear in many real-world data sets, but few visualization methods exist that properly deal with them. parallel Sets are a new method for the visualization and interactive exploration of ca...
详细信息
Categorical data dimensions appear in many real-world data sets, but few visualization methods exist that properly deal with them. parallel Sets are a new method for the visualization and interactive exploration of categorical data that shows data frequencies instead of the individual data points. The method is based on the axis layout of parallel coordinates, with boxes representing the categories and parallelograms between the axes showing the relations between categories. In addition to the visual representation, we designed a rich set of interactions. parallel Sets allow the user to interactively remap the data to new categorizations and, thus, to consider more data dimensions during exploration and analysis than usually possible. At the same time, a metalevel, semantic representation of the data is built. Common procedures, like building the cross product of two or more dimensions, can be performed automatically, thus complementing the interactive visualization. We demonstrate parallel Sets by analyzing a large CRM data set, as well as investigating housing data from two US states.
We have previously shown that random sampling is an effective clutter reduction technique and that a sampling lens can facilitate focus+context viewing of particular regions. This demands an efficient method of estima...
详细信息
We have previously shown that random sampling is an effective clutter reduction technique and that a sampling lens can facilitate focus+context viewing of particular regions. This demands an efficient method of estimating the overlap or occlusion of large numbers of intersecting lines in order to automatically adjust the sampling rate within the lens. This paper proposes several ways for measuring occlusion in parallel coordinate plots. An empirical study into the accuracy and efficiency of the occlusion measures show that a probabilistic approach combined with a 'binning' technique is very fast and yet approaches the accuracy of the more expensive 'true' complete measurement.
In this paper we propose an approach in which interactive visualization and analysis are combined with batch tools for the processing of largedata collections. large and heterogeneous data collections are difficult t...
详细信息
In this paper we propose an approach in which interactive visualization and analysis are combined with batch tools for the processing of largedata collections. large and heterogeneous data collections are difficult to analyze and pose specific problems to interactive visualization. Application of the traditional interactive processing and visualization approaches as well as batch processing encounter considerable drawbacks for such large and heterogeneous data collections due to the amount and type of data. Computing resources are not sufficient for interactive exploration of the data and automated analysis has the disadvantage that the user has only limited control and feedback on the analysis process. In our approach, an analysis procedure with features and attributes of interest for the analysis is defined interactively. This procedure is used for off-line processing of large collections of data sets. The results of the batch process along with "visual summaries" are used for further analysis. visualization is not only used for the presentation of the result, but also as a tool to monitor the validity and quality of the operations performed during the batch process. Operations such as feature extraction and attribute calculation of the collected data sets are validated by visual inspection. This approach is illustrated by an extensive case study, in which a collection of confocal microscopy data sets is analyzed.
暂无评论